© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5636
    Prev
    Next
    INDEX
    Explanations

    abbreviations, variable names, and identifiers commonly used in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Strings of two capitalized letters

    np_acts-logits-general · gemini-2.0-flash

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XH
    -0.66
    PSI
    -0.64
    ZB
    -0.63
    ZM
    -0.62
    IMPORTED
    -0.62
    URI
    -0.60
    XP
    -0.60
    UA
    -0.60
    GG
    -0.60
    JN
    -0.60
    POSITIVE LOGITS
     argint
    0.85
     henkil
    0.79
     húmedo
    0.77
     desmotivaciones
    0.76
     näytte
    0.73
     burbujas
    0.73
     pioggia
    0.71
     uñas
    0.71
     cejas
    0.70
     bocetos
    0.70
    Activations Density 2.373%

    No Known Activations